MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
## Project Overview
npm MIT -
mcp-compressgithub.com/ShipItAndPray/mcp-compressupdated this year
First MCP server for data compression. 60x compression on docs, 30x on SQL, 20x on logs. Zero dependencies. Lossless. Auto-picks best algorithm. 7 tools for any AI agent.
MIT ★ 3 -
mcp-img-compress-ossgithub.com/honghaiyang/mcp-img-compress-ossupdated this year
图片无损压缩与OSS上传MCP工具，可以让AI将项目中的图片资源无损并上传至阿里云 oss 用 cdn 链接替换图片资源
npm MIT -
py-image-compress-mcpgithub.com/crper/py-image-compress-mcpupdated this year
High-performance MCP image compression service for AI assistants with intelligent optimization and batch processing capabilities
MIT ★ 1 -
compression-ai-mcpgithub.com/csoai-org/compression-ai-mcpupdated this year
Compression Ai automation via MCP. Includes estimate ratio, suggest algorithm, calculate savings. By MEOK AI Labs.
npm MIT -
Agentic_context_compression_frameworkgithub.com/saitarrun/Agentic_context_compression_frameworkupdated this year
Rust MCP server for lossless agent-context compression, reducing token usage while preserving retrieval accuracy.
-
Context compression and planning for RAG and AI agents: fit retrieved documents, chat history and tool output into a token budget.
pypi MIT -
logzipgithub.com/NailShakurov/logzipupdated this year
Compress logs for LLM analysis — Rust-powered, Python API. 40-60% token savings.
MIT ★ 12 -
lazy-media-mcpgithub.com/leaf76/lazy-media-mcpupdated this year
Local MCP server: compress images/videos and prepare media for AI vision agents (paths only, no base64). Claude, Codex, and other MCP clients.
MIT ★ 1 -
Pre-injection context compression and session deduplication for AI coding agents: squeeze tool output, code, JSON and logs before they reach the LLM
npm (MIT OR Apache-2.0) -
MCP server for image-and-video-compressor — lets coding agents compress images and videos, probe media, and discover what the local ffmpeg and sharp builds actually support.
npm MIT -
yaktool-image-mcpactive
Local image tools as an MCP server: compress PNG/JPEG with a visually-guarded smart mode or true lossless mode, and convert/resize images to marketplace presets (Amazon, Google Shopping, eBay) with the output rechecked against the platform rules. Same eng
npm MIT -
promptthrift-mcpgithub.com/woling-dev/promptthrift-mcpupdated this year
Smart token compression MCP server for LLM apps. Gemma 4 local compression, multi-model cost tracking, intelligent model routing. Save 70-90% on API costs.
MIT ★ 1 -
MCP server: two-pass Wenyan compression for URLs, files, diffs, logs
★ 1 -
MCP Server for SlimContext - AI chat history compression tools
npm MIT -
token-compressor-mcpgithub.com/base76-research-lab/token-compressorupdated this year
MCP server that compresses prompts 40-60% using local LLM + embedding validation
pypi MIT -
Context-Engine MCP - Agentic Context Compression Suite
MIT ★ 402 -
Pure Python FastMCP Server for Token-Optimized Object Notation (TOON) JSON payload compression
MIT -
A Model Context Protocol server for ZIP compression using fastMCP and zip.js
npm MIT -
zip-mcpgithub.com/7gugu/zip-mcpupdated this year
An MCP tool that provides AI with the ability to compress and decompress local files.
MIT ★ 16 -
tare-aigithub.com/mstuart/tareupdated this year
Lossless-by-default context compression for LLM coding agents — HTTP proxy, CLI, and MCP server.
npm MIT -
Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.
npm Apache-2.0 ★ 677 -
Compress PNG, JPEG & WebP in your browser — nothing uploaded. Offline, MIT.
MIT -
tinify-mcpgithub.com/Stianlars1/tinify-mcpupdated this year
MCP server for Tinify.dev — image compression for AI agents
MIT -
fish-bridge-mcpgithub.com/makeamouse/fish-bridge-mcpupdated this year
Session-scoped knowledge graph engine for AI chat context compression
pypi MIT -
Compress photos to an exact target size (B/KB/MB) — desktop app + MCP server for AI agents
MIT ★ 2 -
Reversible, structure-aware context compression engine for LLM agents (Rust) — cuts token cost of tool outputs, JSON and logs. Deterministic, sans-io, zero network.
npm Apache-2.0 -
Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.
Apache-2.0 ★ 4 -
tokensavergithub.com/pozii/tokensaverupdated this year
MCP server that cuts AI agent token costs by up to 97% — compression, caching, pruning, web extraction
Apache-2.0 ★ 1 -
Do anything with any file: the Filestar command line (filestarcli). Convert, compress and transform thousands of file formats.
npm SEE LICENSE IN LICENSE.md -
MCP server for the Papyrio PDF API: compress, convert, merge, split and OCR PDFs from an assistant.
npm MIT -
Bulk image optimizer CLI — compress, resize, convert JPEG/PNG/WebP/AVIF. Interactive mode, MCP server for AI editors, watch mode, git hooks. Free.
npm AGPL-3.0-only -
taregithub.com/mstuart/tareactive
Lossless-by-default context compression for LLM coding agents — proxy, library, CLI, and MCP server. Local-first, cache-correct, reversible.
MIT ★ 5 -
On-device image tools for AI agents (MCP): background removal, compression, resize, crop, AI upscale, metadata removal. Images never leave your computer.
MIT -
token-lens-mcpgithub.com/mdfifty50-boop/token-lens-mcpupdated this year
MCP server for analyzing and optimizing context window token usage — audit tool definitions, compress schemas, track usage, and reduce bloat
npm MIT -
codebase-pilot-cligithub.com/kalpeshgamit/codebase-pilotupdated this year
Claude Code context engine — pack, compress, and optimize any codebase for AI. Save 60-90% tokens.
npm MIT -
frogConvert lets you securely convert between 70+ formats, compress files, and manage your PDFs, right in your browser. Your files never leave your device.
GPL-3.0 ★ 3 -
fullscopegithub.com/justguy/fullscopeupdated this year
See more code. Get better answers. Context optimization MCP server for LLMs — compresses code structurally so models can reason over entire files without losing logic.
npm MIT -
@csc-protocol/token-saveractive
Autonomous AI agent tool and MCP server for semantic token compression and L402 edge solvency clearance.
npm UNLICENSED -
Agent Intermediate Language (AILv1): Zero-loss AI context compression protocol, AST signature extractor, and MCP server that cuts LLM handoff tokens by 85–95%.
MIT ★ 1 -
Compress, resize, crop and convert images (JPG, WebP, PNG) locally, no uploads. Web UI plus an MCP server so AI agents can optimize your project's images.
npm MIT -
agentready-cloud-mcpactive
MCP server for AgentReady: compress prompts with TokenCut and turn any URL into clean, token-light Markdown, inside Claude, Cursor, Windsurf and any MCP client.
npm MIT -
toonify-mcpgithub.com/PCIRCLE-AI/toonify-mcpupdated this year
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
MIT ★ 67 -
Codex plugin MCP server (codex-plugin-mcp) for token efficiency, token reduction, context compression: exact-recoverable terminal, file, project, web, memory.
MIT ★ 4 -
Dual-licensed hosted compression client, quotes, checkout, and MCP. Open license or a paid grant. First 1 GB free (once per IP), then 25¢/GB.
npm (AGPL-3.0-or-later OR LicenseRef-SlidPhiLabs-Commercial) -
Context selection and compression for AI agents — with the recall measured, not claimed. One file, no dependencies.
MIT -
Model Context Protocol server for CyberChef — exposes GCHQ's "Cyber Swiss Army Knife" as AI-agent tools: 504 operations across encryption, encoding, compression and forensics, on MCP protocol revision 2026-07-28
npm GPL-3.0 ★ 34 -
cctxgithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% using a free local LLM (Ollama). MCP server + Stop hook with codebase indexing, tool output compression, and turn summarization.
MIT ★ 3 -
Smart Context Engineering Gateway for AI agents: lossless tool-output compression, episodic memory folding and a reversible diet_ref vault (MCP server + OpenAI/Anthropic proxy + local dashboard)
MIT -
codebase-pilotgithub.com/kalpeshgamit/codebase-pilotupdated this year
AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.
MIT ★ 6 -
Long-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
MIT ★ 25 -
token_optimizergithub.com/omkar9854/token_optimizerupdated this year
Zero-dependency, fully-reversible context compression for AI agents — cut LLM token usage up to 94% (JSON tabularization, log template mining, query-aware code skeletons). Stdlib-only, air-gap ready, built-in MCP server.
Apache-2.0 ★ 1 -
Measure what context compression actually costs an LLM agent: where a session's tokens go, and whether a rewrite pays for the prompt cache it invalidates. Rust crate, MCP server and benchmark harness.
MIT ★ 1 -
Self-hosted AI workspace that compresses prompts before they leave your machine — 79% fewer tokens, measured. Drop-in gateway for Claude Code, Cursor, Aider and any OpenAI/Anthropic client, plus an MCP server. Free, MIT, zero telemetry.
MIT ★ 2 -
Free browser PDF tools: merge, split, compress, Word to PDF, PDF to Word/Excel/PowerPoint, images and English OCR. On-device documents; no uploads or account. Local MCP tool discovery. Source-available, noncommercial license.
NOASSERTION -
Local MCP server with exact file tools for AI assistants: compress, resize and convert images (HEIC, WebP, AVIF), strip EXIF/GPS metadata, make and read QR codes, exact text counts, diff, JSON validation. Files never leave your computer.
MIT -
cctx-optimizergithub.com/anil7948/cctxupdated this year
Reduce Claude Code token usage by 70-90% with cross-session memory and four-layer optimization: semantic codebase indexing, PostToolUse tool compression, turn summarization, and session consolidation. MCP server powered by Ollama — zero API calls, runs en
npm MIT -
Verified context for AI coding agents. A local context layer that intelligently compresses, filters, indexes, and verifies AI coding-agent tool output. 32 MCP tools across 10 layers: code intelligence (tree-sitter, 30+ languages), context selection, tool
npm SEE LICENSE IN LICENSE -
yaktool-pdf-mcpactive
PDF organisation as an MCP server: merge, split, compress image-heavy files, unlock password-protected ones with the password you supply, rewrite the page order with relative rotation, and check whether a redacted PDF actually removed the text — recoverab
npm MIT -
Official MCP server of the Conv2pdf API: an AI assistant converts Office documents, images, e-books and web pages to PDF, and merges, splits, compresses, protects or converts the PDFs of your computer. Hosted in the EU (France).
npm MIT